Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Putot, Sylvie"'
Autor:
Goubault, Eric, Putot, Sylvie
We propose an approach to compute inner and outer-approximations of the sets of values satisfying constraints expressed as arbitrarily quantified formulas. Such formulas arise for instance when specifying important problems in control such as robustn
Externí odkaz:
http://arxiv.org/abs/2309.07662
This paper presents a method for determining the area explored by a line-sweep sensor during an area-covering mission in a two-dimensional plane. Accurate knowledge of the explored area is crucial for various applications in robotics, such as mapping
Externí odkaz:
http://arxiv.org/abs/2309.03604
Neural ordinary differential equations (NODEs) -- parametrizations of differential equations using neural networks -- have shown tremendous promise in learning models of unknown continuous-time dynamical systems from data. However, every forward eval
Externí odkaz:
http://arxiv.org/abs/2201.05715
Publikováno v:
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:263-277, 2022
Effective inclusion of physics-based knowledge into deep neural network models of dynamical systems can greatly improve data efficiency and generalization. Such a-priori knowledge might arise from physical principles (e.g., conservation laws) or from
Externí odkaz:
http://arxiv.org/abs/2109.06407
Publikováno v:
In International Journal of Approximate Reasoning June 2024 169
Autor:
Goubault, Eric, Palumby, Sébastien, Putot, Sylvie, Rustenholz, Louis, Sankaranarayanan, Sriram
This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to specifications and reachability analysis of neural-network feedback sys
Externí odkaz:
http://arxiv.org/abs/2108.00893
We study learning based controllers as a replacement for model predictive controllers (MPC) for the control of autonomous vehicles. We concentrate for the experiments on the simple yet representative bicycle model. We compare training by supervised l
Externí odkaz:
http://arxiv.org/abs/2107.14573
Autor:
Bernini, Nicola, Bessa, Mikhail, Delmas, Rémi, Gold, Arthur, Goubault, Eric, Pennec, Romain, Putot, Sylvie, Sillion, François
We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller. We provide all details allowing to reproduce our approach, starting with a model of the dynamics of a craz
Externí odkaz:
http://arxiv.org/abs/2107.12942
Autor:
Goubault, Eric, Putot, Sylvie
We consider the problem of under and over-approximating the image of general vector-valued functions over bounded sets, and apply the proposed solution to the estimation of reachable sets of uncertain non-linear discrete-time dynamical systems. Such
Externí odkaz:
http://arxiv.org/abs/2101.11536
We develop data-driven algorithms for reachability analysis and control of systems with a priori unknown nonlinear dynamics. The resulting algorithms not only are suitable for settings with real-time requirements but also provide provable performance
Externí odkaz:
http://arxiv.org/abs/2011.05524